Explore our
open source LLMs
and AI models

Access powerful, production-ready language models and AI solutions
openly available through Prodoc AI's commitment to open source

hello

EndConvo SLM

EndConvo-health-1b-GGUF-v1 is a fine-tuned version of the Llama3.2-1B model, trained on a dataset of healthcare-related conversations with the purpose of identifying whether a conversation has ended. This model helps to avoid unnecessary responses from larger language models by detecting closing statements.

Model Objective

The model analyzes healthcare conversations and outputs a binary classification:

True

Conversation has reached its natural conclusion

False

Conversation is still ongoing and active

Dataset Information

Training Data Statistics
  • Total Conversations: 11,798
  • Chat Count: 94,472
  • Average Chats per Conversation: ~8
  • Custom dataset of 4,000 rows focused on healthcare conversations
Dataset Overview

This healthcare-focused conversational dataset includes 11,798 unique conversations, with an average of 8 messages per conversation. The dataset consists of conversations in a variety of languages with the following breakdown:

  • English (en): 78,404 messages
  • Marathi (mr): 2,092 messages
  • Hindi (hi): 2,857 messages
  • Additional languages included as per Language Map section

Ollama Integration

Experience seamless integration with Ollama, where the model is fully hosted and ready to run. Simply execute the command below to start utilizing the model's capabilities in identifying conversation endpoints efficiently and effectively.

ollama run Prodoc/endconvo-health-1b

Enjoy the ease of deployment and the power of advanced conversational analysis with Ollama.

Intent Classification SLM

HealthIntent-Classifier-1b-GGUF-v1 is a fine-tuned version of the Llama3.2-1B model, trained to classify healthcare-related queries into predefined intents. This model is designed to streamline user interactions by identifying their specific healthcare-related needs efficiently.

Model Details

  • Model Name: Intent-classification-1b-GGUF-v1
  • Base Model: Llama3.2-1B
  • Number of Parameters: 1 Billion
  • Dataset: Custom dataset of healthcare-related conversation
  • Languages: Includes en, mr, te, hi, bn, among others (detailed in Language Map section)

Model Objective

The model identifies the intent behind healthcare-related queries and classifies them into one of the predefined categories. This allows for better routing and handling of user requests in healthcare systems.

Supported Intents

  • Appointment Booking
  • Surgery Enquiry
  • Emergency Assistance
  • Lab Test Results Inquiry
  • Symptom Consultation
  • Hospital Services Enquiry
  • Job or Internship Enquiry
  • Complaint or Feedback
  • Health Check-Up Packages
  • Health Insurance Enquiry
  • Irrelevant Query

Ollama Integration

Leverage seamless integration with Ollama, where the model is fully hosted and ready to run. Simply execute the command below to start utilizing the model's intent classification capabilities. Transform your healthcare conversational systems with precision and ease.

ollama run Prodoc/intent-classification-1b